Hacker News

Is there a significant difference between Claude Code in VSCode and Copilot in VSCode? I’ve been using Copilot with the Claude models (including Sonnet/Opus 4.6) and it seems to work spectacularly.

My subscription is only $10 a month, and it has unlimited inline suggestions. I just wonder if I’m missing anything.

Not a real solution but you could try using AquaVoice for dictation. It can gather screen context so you just say the function name out loud and it capitalizes and spells everything correctly. (Even hard cases!)

I think it would be fantastic to have a reference site for significant, complex projects either developed or substantially extended primarily via agent(s). Every time I look at someone's incredible example of a workflow for handling big context projects, it ends up being a greenfield static microblog example with vague, arm-wavey assertions that it will definitely scale.

They’re not experts.

> does not imply working on multiple features at one time.

How can multiple parallel agents some local and some in the cloud be working on a single task?

How can:

> All local and cloud agents appear in the sidebar, including the ones you kick off from mobile, web, desktop, Slack, GitHub, and Linear. (From the announcement, under “Run many agents in parallel”)

…be working on the same task?

Subagents are different, but the OP is not confused about what cursor is pushing, and it is not what you describe.

Have you tried Devswarm.ai yet? It's similar but can use VS Code workflows.

I have personally found that I cannot context switch between thinking deeply about two separate problems and workstreams without a significant cognitive context-switching cost. If it's context-switching between things that don't require super-deep thought, it's definitely doable, but I'm still way more mentally burnt-out after an hour or two of essentially speed-running review of small PRs from a bunch of different sources.

Curious to know more about your work:

Are your agents working on tangential problems? If so, how do you ensure you're still thinking at a sufficient level of depth and capacity about each problem each agent is working on?

Or are they working on different threads of the same problem? If so, how do you keep them from stepping on each other's toes? People mention git worktrees, but that doesn't solve the conflict problem for multiple agents touching the same areas of functionality (i.e. you just move the conflict problem to the PR merge stage)

> Personally waiting for one agent to do something while I shove my thumb up my butt just waiting around for it to generate code that I'll have to fix anyway

I spend that time watching it think and then contemplating the problem further since often, as deep and elaborate as my prompts are, I've forgotten something. I suspect it might be different if you are building something like a CRUD app, but if you are building a very complicated piece of software, context switching to a new topic while it is working is pretty tough. It is pretty fast anyway and can write the amount of code I would normally write in half a day in like 15 minutes.

I find it puzzling whenever someone claims to reach "flow" or "zen state" when using these tools. Reviewing and testing code, constantly switching contexts, juggling model contexts, coming up with prompt incantations to coax the model into the right direction, etc., is so mentally taxing and full of interruptions and micromanagement that it's practically impossible to achieve any sort of "flow" or "zen state".

This is in no way comparable to the "flow" state that programmers sometimes achieve, which is reached when the person has a clear mental model of the program, understands all relevant context and APIs, and is able to easily translate their thoughts and program requirements into functional code. The reason why interrupting someone in this state is so disruptive is because it can take quite a while to reach it again.

Working with LLMs is the complete opposite of this.

For my work I’ve never found myself sitting around with nothing to do because there’s always so much review of the generated code that needs to be done

The only way I can imagine needing to run multiple agents in parallel for code gen is if I’m just not reviewing the output. I’ve done some throwaway projects where I can work like that, but I’ve reviewed so much LLM generated code that there is no way I’m going to be having LLMs generate code and just merge it with a quick review on projects that matter. I treat it like pair programming where my pair programmer doesn’t care when I throw away their work

Why is this comment so pale I cat read it? What’s the contrast on this is this accessible to anyone?

I’m guessing it was downvoted by the masses but at the same time I’d like the choice to be able to read it I’m not that into what the general public think about something.

I’m getting into downmaxxing at this point. I love that you have to earn being negative on this site. Give it to me.

Why is it that every legitimate concern or downside pointed out about AI is met with the same tired, low signal, rebuttal of FOMO.

It's become the "no u r" argument of the AI age... :/

"I have never woodworked a day in my life, with Claude Carpenter I don't have to touch the work at all and can just vaguely ask for things and pray that it does something useful."

There’s a reason it’s 10x cheaper. You’ll be paying the real price after the subsidies end.

> Anyway, you’re right Claude Code is less ergonomic; generally slower.

The secret in my experience is parallelization - Cursor might be faster or have better ergo for a single task, but Claude Code really shines when you have 6 tasks that are fairly independent.

If you treat CC as just another terminal tool and heavily use git worktrees, the overall productivity shoots through the window. I've been using a tool called Ouijit[1] for this (disclosure: the dev is an old colleague of mine), and I genuinely do not think I could go back to using Cursor or any other traditional IDE+agent. I barely even open the code in an editor anymore, primarily interacting through the term with Vim when I need to pull the wires out.

[1]: https://github.com/ouijit/ouijit

long term claude code user here, never used cursor, however based on my limited experience, it seems codex can code better than claude code.

There is no Max sub for enterprise AFAIK, are you using a private plan for work?

My company is going through the exact opposite, so it kinda depends on the company. We are actively encouraging our devs to NOT use Cursor because of how much more expensive it is compared to other tools we have from our calculations and they even considered dropping Cursor at contract renewal altogether due to their costs being higher than other tools.

2x intelligence != 2x results

most tasks I can do better and faster with composer 2

a fellow engineer reported a bug on a code I had written a few months back. I used his report as prompt for composer 2, gpt-5.4-high and claude-4.6-opus-max-thinking. composer found the issue spot on. gpt found another possible vector a couple of minutes later, but a way less likely one and one that would eventually self heal (thus not actually reproducing what we observed on production). claude had barely started when the other two had finished

also, i don't have a budget per se. but it is expected that i over deliver if i'm over spending

Because they are twice as stupid.

yeah good point. I think this is to be seen though. Right now AI tokens, especially via OpenAI/Anthropic subscriptions, are heavily subsidized. If token cost between the API and subscriptions should even out though, then I think Cursor might well be back in the race.

I wanted to like zed, but then I discovered it is limited to one concurrent agent tab and that is a dealbreaker..

The premise of Zed is quite appealing, but I'm not sure I'm ready to switch due to the missing extension ecosystem of VSC. For example, at the moment I'm using the Playwright and Vite ones to quickly run and debug tests.

Zed is incredible, such a relief

How does Zed compare to let's say vsc

> It's a very tough spot they're in.

It's a very tough spot they put themselves into. If the goal wasn't to get filthy rich quick it would probably be possible to make a good product without that tough spot.

As these products mature people are going to see more of this stuff. These are the contours of the market. The technology is incredible but it’s still subservient to the economics of building products.

It’s the “why can’t Facebook just show me a chronological feed of people I follow”. Because it’s not in their interests to do so.

It's heartbreaking to write this, but I think Cursor will be remembered as the Lotus 1-2-3 of AI coding.

It is interesting that i find composer to be one of my favorites as while it is a bit dumb it is about 100x faster than the fat boys.

Sometimes u need the beef of opus but 80% composer is plenty.

Tried the cursor a few times, apart from a fancy layer on top of VS Code, it is way too expensive to use, it runs out of credit in a few tasks. On the other hand, vs code with copilot is slower and less 'intelligent', but it lasts longer, I get more work done with it. Recently, started using opencode inside vs code, it is similar to claude code, but needs some better integration with vs code.

> They've obviously had a go at being a first-party model company to address this, but that didn't work.

I thought there was an entire initiative to build their own coding model and the fine tunes of in Composer 1.5 and Composer 2 were just buying them time and training data

You know, it’s stuff like this making me think maybe the anti capitalists have a point.

A company makes a popular product customers like, but to satisfy the VCs the company must make a product the customers don’t like but could make the VCs more money.

Not sure this is the “invisible hand” Adam Smith had in mind.

The cancer: growth at every cost or die.

God forbids you make a great product in a specific niche and are happy with the money flowing.

Nope, has to be more.

We're building DevSwarm, and it's aiming to strike the balance between agentic coding in parallel without losing your IDE. Each workspace (worktree) gets a dedicated vscode instance, and in that instance we make it easy to fire up Claude Code, Codex, etc. Would love to hear if it hits the sweet spot we're going for.

edit: https://devswarm.ai

This is why I use Claude Code though, it pairs well with a regular old text editor (in my case Sublime). I've always had an editor and a terminal open, plugging an AI into my terminal has been a fantastic enhancement to my work without really anything else changing or giving up any control.

I actually run a custom fork of Zed based on their master branch because of how stagnated the built-in agent is. Master branch Zed agent did get sub-agents, parallel threads, better thread management, and worktrees though, and I implemented agent skills and the ability to select which model to use for sub-agents for it. And with those features, I'm fairly satisfied.

did you watch the 90 second video in the post? all of this is addressed

It’s very unfortunate what direction Zed has taken. It was very fast and nice editor, that’s now infected with those “AI” features.

I'm an engineer at Cursor, can try to clarify questions here.

> I wish they'd keep the old philosophy of letting the developer drive and the agent assist. Even when I'm using AI agents to write code, I still find myself spending most of my time reading and reasoning about code.

We very much still believe this, which is why even in this new interface, you can still view/edit files, do remote SSH, go to definition and use LSPs, etc. It's hard to drive and ship real changes without those things in our opinion, even as agents continue to get better at writing code.

> I'm hoping in this new UI in v3 I can still get that experience (maybe it's just hidden behind a toggle somewhere for power users / not shown off in the marketing materials).

This new interface is a separate window, so if you prefer the Cursor 2 style, that continues to exist (and is also getting better).

> It's been the perfect in-between of coding by hand (never again!) and strictly "vibe coding" for me.

I dont think there is an inbetween. Its really hard to 'keep an eye' on code by casually reading diffs. Eventually it will become vibe coding.

Software engineers are deluding themselves with spec driven, plans, prds whatever nonsense and thinking its not vibecoding.

Isn’t Cursor’s business model mostly subscriptions? They’re the ones paying for inference, not the user directly, right? So wouldn’t they be incentivized to minimize token usage per unit of user value, not maximize raw tokens?

Does Cursor make money from tokens?

I thought it was primarily a user of Anthropic and OpenAI APIs, so the fewer tokens you use to accomplish a task, the higher their margin.

Claude Code is where you move up one abstraction layer. Almost everyone using it productively has spend a lot of time working on their harness, ensuring that everything is planned out and structured such that all that is left is really type in the code. This typically works without error. Before that, you interact a lot via Claude Code in whatever abstraction you feel is right.

That's basically it. You can review changes afterwards, but that's not the main point of Claude Code. It's a different workflow. It's built on the premise: given a tight and verifiable plan, AI will execute the actual coding correctly. This will work, mostly, if you use the very best models with a very good and very specific harness.

Cursor, same as Copilot, has been used by people who are basically pair programming with the AI. So, on abstraction down.

I have no idea what is better, or faster. I suspect it depends at least on the problem, the AI, and the person.

It's good to try Claude Code just so you focus on skills, agents, and CLAUDE.md

Then when you go back to Cursor it will still support all of those things in the settings.

Using Cursor you tend to not think about those as much since Cursor does a lot of it for you as part of the IDE integration. But it's good to refine it your own way.

But for the most part there isn't much difference.

You don't have to stop using the IDE just because you are using Claude Code. Using both at the same time is best of both worlds in my experience.

Claude Code isn't really "all terminal" if you embed that terminal in your IDE. I still use Cursor (for now), but I embed a CC panel via extension. With this launch of Cursor 3, I'll probably get off Cursor for good. I have zero interest in this.

As someone whose work enforced a switch from Cursor to Claude Code, I do keep on top of the code by pairing it with an IDE, tracking/viewing changes etc. There's no real obstacle to using an IDE as you normally would, with Claude Code as a sidecar.

I run Claude Code from Zed. Very nice experience.

Yeah that's the disconnect though right? Even with the best frontier models, you need to do a lot of system design work, planning, and reviewing before you can let these models run.

These models are infinitely more effective when piloted by a seasoned software engineer and that will always be the case so long as these models require some level of prompting to function.

Better prompts come from more knowledgeable users, and I don't think we can just make a better model to change that.

The idea we're going to completely replace software engineers with agents has always been delusional, so anchoring their roadmap to that future just seems silly from a product design perspective.

It's just frustrating Cursor had a good attitude towards AI coding agents then is seemingly abandoning that for what's likely a play to appease investors who are drunk on AI psychosis.

Edit: This comment might have come off more callous than I intended. I just really love Cursor as a product and don't want to see it get eaten by the "AI is going to replace everything!" crowd.

AI labs won't replace all of the engineers, while engineers becoming more productive, leads to smaller team sizes.

> AI labs think they’re building an autonomous replacement for software engineers

And management everywhere is convinced that thats what they are paying for. My company is replacing job titles with "builder". Apparently these tools will make builder out of paper pushers hiding in corporate beaurcarcy. I am suddenly same as them now per my company managment.

Cursor CLI exist - https://cursor.com/cli

There are some critical parts of architecture where sometimes I really do need to see the code and even sometimes put a wall around it and tell the agent they can't touch it.

Why?

Are you saying they can’t compete with VS Code in the semi-automatic space?

Saying it can't stay in between is like saying a company can't sell both regular bikes and electric bikes. Or bikes that can do both.

Works until you discover subtle bugs hiding behind ugliness.

They're targeting the 90% of code that doesn't really need to be looked at. Software is already so complex and interconnected that it is fully beyond human capabilities, each person only knows a tiny part of the stack. If you create your own full system from scratch, it's not going to be very generally useful.

NASA vibes all its note taking apps

I hope this comes off as constructive criticism, but I'm confused about what cursor is now.

Cursor is an IDE and an agentic interface and a cli tool and a platform that all work locally and and in the cloud and in the browser and supports dozens of different models.

I don't know how to use the thing anymore, or what the thing actually is.

Let me give this a shot:

Cursor was the tool you use to pair program with AI. Where the AI types the code, and you direct it as you go along. This is a workflow where you work in code and you end up with something fundamentally correct to your standards.

Claude Code is the tool you use if you want to move one abstraction layer up - use harness, specs, verifications etc. to nail down the thing such that the only task left is type in the code - a thing AI does well. This is a workflow where the correctness depends on a lot of factors, but the idea is to abstract one level up from code. Fundamentally, it would be successful if you don't need to look at code at all.

I think there is not enough data to conclusively say which of these two concepts is better, even taking into account some trajectory of model development.

I do feel that any reason I have for installing Cursor is that I want to do workflow 1, rather than workflow 2. Cause I have a pretty comprehensive setup of claude code (or opencode, or whatevs) and I think it does everything you list here.

So, as a product engineer, you probably wanna mention why it matters that Cursor UI allows you to edit files with auto-complete.

I would switch to Cursor 3 in a heartbeat if it supported Claude Agent SDK (w/ Claude Max subscription usage) and/or Codex the way that similar tools like Conductor do

And I would happily pay a seat based subscription fee or usage fees for cloud agents etc on top of this

Unfortunately very locked into these heavily subsidized subscription plans right now but I think from a product design and vision standpoint you guys are doing the best work in this space right now

Is there going to be any more development on the frontier of cursor tab completion and features like that (more focused on helping engineer's with llm's for complex tasks) since I feel this is the main reason I dont use claude code or codex. I want to be writing the code, since I want performant, small, codebases that I understand (I am writing eBPF stuff, so agentic coding doesnt work that well)

Computer use in the cloud for me is THE killer feature.

vscode + claude code extension has everything you listed that actually matters

You can use almost any model with Claude Code.

Yep, Composer 2 has been quite good for me too. I only turn to Opus for major brainteasers.

the codex limits are actually pretty high too. You might want to check it out.

You can do this with copilot, for the $40/mo range, AND you get to use opus 4.6 for all of it. Copilot is absurdly cheap if you can make it fit your work profile.

I mean, in that case, cannot you do the same by just using sonnet instead of opus?

My man, have seen the Sonnet 4.6 tho

That gap was closed by opencode months ago.

> So to answer your question: they would be forking Atom (which I think would’ve won otherwise).

Atom was far slower than VS Code, despite both of them being built on Electron. I wouldn't have used Atom, but I use VS Code.

It is entirely possible that some other closed-source editor with a superior package/extension system would have won, or the "war" would have been postponed until Rust was ready enough for Zed to come along.

Sublime Text fell because VS Code was just better, not because it was closed source. I switched from Sublime Text to VS Code, and didn't care one bit how open or close either was.

Not saying there aren't people who care, there are, but they are a small minority.

There is even a cli version of cursor.

https://cursor.com/cli

Oh my god, this comment gave me flashbacks to when I was writing android apps in Eclipse + ADT

And Eclipse Foundation maintains VSCode-compatible editor designed to be a framework for other IDEs: https://theia-ide.org/

IMO sounds like natural foundation for Cursor

shudders does anyone pine for eclipes?

I haven't used it in a decade, Im sure it has has evolved

There is a large and growing segment of executives in the software world that is pushing this model hard, like betting their career on it. To them the “dark factory” is an inevitability. As a consequence, not only are developers choosing this path, but the companies they work for are in varying degrees selecting this path for them.

The agents aren't going to orchestrate themselves.

You also don't need to write or read the code to build great software.

This is how many high output teams are working now:

- Human writes PRD (usually with help of agent)

- Agent breaks down PRD into engineering specs with human review and input on and on technical implementation (architecture decisions, etc)

- Team of agents implement PRDs

- Team of agents reviews PRDs and checks for fidelity against both PRD and spec, fixing automatically or asking human for input if PRD or spec is unclear

- Team of agents tests final work product against spec and presents to human for final verification

Humans writing code manually is over.

Humans reviewing code manually and in-detail is mostly over.

Humans directing high-level architecture is still here for now but will likely be reduced in the near future.

Saying how many lines of code you can write this way is also a bit like bragging that you are building world's heaviest airplane.

It’s not their code, and it’s not for them to understand. The endgame here is that code as we know it today is the “ASM” of tomorrow. The programming language of tomorrow is natural human-spoken language used carefully and methodically to articulate what the agent should build. At least this is the world we appear to be heading toward… quickly.

Reminds me of these "if you don't pay 200 dollars per month for AI you are NGMI" comments...

Well I’m a software engineer and code more than 4 hours per day.

But I do check the generated code, make sure it doesn’t go banana. I wouldn’t do multiple features at the same time as I have no idea how people are checking the output after that.

I like AI coding and it accelerated my work, but I wouldn’t trust their output blindly

Zed is not a fork of VS Code. It is one of the few genuine new editors in the last few years. Written in Rust and much smoother than VS Code and its forks.

Maybe I'm just behind on the features, I didn't even know there was an agents window. There's an agents sidebar.

Me too, I have the bad feeling autocomplete will be sunsetted sooner or later, it clearly isn't the path they're getting into. Also it started to get worse lately, it tries too hard to predict, it wasn't like that some time ago, hopefully you know what I'm saying

I assume they meant that "Claude Code is so good..." and that they cancelled Currsor and just use CC + VSCode.

I agree with you but what they're launching here is not a beautiful GUI. It's minimalist (in a bad way) and not really innovative.

Wow, maybe something is wrong with my setup. In Cursor 3, I am clicking "New Agent" at the top left. My root repository is correctly listed on top of the composer, and I clicked the icon to the right of it and selected 'Worktree'. Then, I instruct the model to run `pwd` and tell me it's git status. It's always just on `main` in my root repository. I dug through the settings and couldn't find anything, and after finding this comment[0] on their forums gave up. Would you mind sharing a bit more about your setup/how it works?

[0] https://forum.cursor.com/t/working-with-worktrees-in-cursor/...

You really need to keep them on a tight leash, stop and correct them when they start screwing up, and then the remaining 90% of the work starts after they say their done, where you need to review/refactor/replace a lot of what they produced.

The only way you're going to let an agent go off on its own to one-shot a patch is if your quality bar is merely "the code works."

This, at least for me, has changed in the past six months. Which is the same thing people were saying in the months prior to that, so I will accept some eye rolls. But at least for our pretty large monorepo opus + a lot of engineering work on context got us to a point where a large portion of our engineers are doing most of their work with agents first and a lot of back and forth + smaller hand edits.

Not true. As long as you don't blindly accept their garbage and keep things behind sensible interfaces so you can reimplement if necessary, and have good tests you're fine

I am using it on fedora from the yum repo and it's crashing for me too.

  $ rpm -q cursor
  cursor-3.0.4-1775123877.el8.x86_64

Apparently if launched with --verbose it works, but that's the same crash I was seeing without the verbose flag

I prefer to avoid AppImages if I can but I gave it a try anyway and it still fails with exactly the same error. What made you think it's just a packaging issue?